Research

Single-option 10-order knock-on effect tracing for decisions and changes.

Runs the complete research pipeline: Brainstorming → Planning → Implementation → Testing & Visualization → Reporting. Orchestrates all phases with user checkpoints between each.

Searches academic literature via OpenAlex (240M+ works) and optionally web sources. Standalone skill for quick literature discovery without the full brainstorm pipeline.

Generates a structured markdown research report from all previous phase outputs. Actively integrates existing plots, generates missing visualizations, and cross-verifies claim-evidence integrity. Requires at least some prior phase results to exist.

Generates high-quality explanations of concepts using Gemini and Codex in parallel (Phase 1: MAGI strategy exploration), then synthesizes a single-voice explanation with Claude (Phase 2: convergent generation).

Executes the research code in `src/` to generate result artifacts in `results/`. This is Phase 3.5 of the research pipeline, sitting between Implementation (Phase 3) and Testing & Visualization (Phase 4).

Generates and cross-validates research ideas using Gemini and Codex in parallel, then synthesizes results with Claude.

Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges everything into the template that already contains Intro + Related Work from Step 3. TRIGGER when the orchestrator delegates Step 4 or when the user asks to "write the methodology and ex...

Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator delegates Step 1 or when the user asks to "outline a paper from raw materials" or "generate the paper structure".

Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to flag hallucinated citations, build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the...

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".

Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimental_log.md). TRIGGER when the user says "aggregate my agent logs for paper writing", "extract experiments from my coding agent history", "prepare PaperOrchestra inputs from my cache", "turn my agent logs into a paper", mention...

Conduct preliminary research on a target topic and generate a research outline. Used for academic research, benchmark research, technology selection, and similar scenarios.

Read research outline and launch independent agents for in-depth research on each item. Task output disabled.

Add items (research subjects) to existing research outline.

Add field definitions to existing research outline.

Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask 学习一下/深入研究/研究一下/整理成文章/deep dive/compile sources or need one coherent reference from many inputs. Not for quick lookups or single-file reads.

Assess and improve Primr output quality. Use when the user asks to review, grade, refine, or troubleshoot a report or strategy document.

Retrieve and update company hypotheses in Primr. Use when the user asks what is already known, wants to validate a claim, or wants to persist a research finding.

Run end-to-end company research through Primr. Use when the user asks to research a company, provides a company URL, or wants a new strategic analysis run.

Run and monitor company research through Primr MCP. Use when the user wants a new research run, asks for status, or needs mode selection help before starting.

Generate a consultant-grade strategic intelligence brief on a company. Long-running (35-120 min) and metered ($0.10-$5). Use when the user asks for a primr report / full strategic dossier / deep company brief, or names a company alongside research-it-with-primr / generate-the-strategic-overview / build-the-AI-strategy / get-the-full-report language. Skip for quick web research (use the host's built-in search and reasoning instead) or DNS-only intelligence (shell out to dig or a passive-recon ...

End-to-end research loop. Use at the start of any new research task; triggers literature review, hypothesis generation, Elo selection, experimentation, and verification.

Run a counterfactual ("what if we had approved hyp_07 instead of pruning it") against a saved snapshot without mutating the live graph. Use when the user wants to second-guess a paused branch or audit a past pruning decision.